Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-571
Open-source VLMs (LLaVA, MiniGPT-4, InstructBLIP) are substantially more vulnerable to multimodal jailbreak attacks than Gemini-1.5-flash, with BAP attack ASR of 58–62% versus 40–41%